RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can FastVLM 0.5B run on the RTX 4080?

Yes. At 8K context the best fit is F16, using about 2.2 GB of the 15.2 GB usable on the RTX 4080. Estimated speed ceiling: ~472 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.0 GB Fits1.0 GB Fits1.3 GB Fits2520
3-bit (Q3_K_M)1.1 GB Fits1.1 GB Fits1.4 GB Fits1933
4-bit (Q4_K_M)1.2 GB Fits1.2 GB Fits1.5 GB Fits1546
5-bit (Q5_K_M)1.2 GB Fits1.3 GB Fits1.6 GB Fits1326
6-bit (Q6_K)1.3 GB Fits1.4 GB Fits1.6 GB Fits1152
8-bit (Q8_0)1.5 GB Fits1.5 GB Fits1.8 GB Fits889
16-bit (F16/BF16)2.2 GB Fits2.2 GB Fits2.5 GB Fits472

• real GGUF file size. Speed is a bandwidth ceiling (717 GB/s), not a benchmark. Methodology.

More

FastVLM 0.5B on every GPU and Mac · Every model that runs on the RTX 4080 · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (apple/FastVLM-0.5B), NVIDIA specs. Data as of 2026-11-17.